Human Activity Classification With Radar: Optimization and Noise Robustness With Iterative Convolutional Neural Networks Followed With Random Forests.

The accurate classification of activity patterns based on radar signatures is still an open problem and is a key to detect anomalous behavior for security and health applications. This paper presents a novel iterative convolutional neural network strategy with an autocorrelation pre-processing instead of the traditional micro-Doppler image pre-processing to classify activities or subjects accurately. The proposed strategy uses an iterative deep learning framework for the automatic definition and extraction of features. This is followed by a traditional supervised learning classifier to label different activities. Using three human subjects and their real motion captured data, 12 000 radar signatures were simulated by varying additive white Gaussian noise. In addition, 6720 experimental radar signatures were captured with a frequency-modulated continuous radar at 5.8 GHz with 400 MHz of instantaneous bandwidth from seven activities using one subject and 4800 signatures from five subjects while walking. The simulated and experimental data were both used to validate our proposed method, with signal–noise ratio varying from −20 to 20 dB and with 88.74% average accuracy at −10 dB and 100% peak accuracy at 15 dB. The proposed iterative convolutional neural networks followed with random forests not only outperform the feature-based methods using micro-Doppler images but also outperform the classification methods using other types of supervised classifiers after our proposed iterative convolutional neural network. [ABSTRACT FROM AUTHOR]